Qian Chen

I am currently woring on Audio department of Consumer Bussiness Group, Huawei Co., and receiced the Ph.D. degree of the School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, China. My research was focusing on interpretable deep learning and intelligent mechanical fault diagnosis.

---

Basic information

Related links:

• Google Scholoar;
• ORCID;
• ResearchGate;

Education & employment background:

• 2025 - now, working on Audio department of Consumer Bussiness Group, Huawei Co., China.

• 2020 - 2025, studying for Ph.D degree of mechanical Engineering at Shanghai Jiao Tong University, Shanghai, China.

• 2016 - 2020, received Bachelor degree of Mechatronic Engineering at Harbin Institute of Technology, Harbin, China.

Interests:

• Active noise cancellation of earphone.
• Mechanical fault diagnosis based on deep neural networks.
• Interpretable AI.

Publication

Paper:

1. Q. Chen, et al., “SHapley Estimated exPlanation (SHEP): A Fast Post-Hoc Attribution Method for Interpreting Intelligent Fault Diagnosis,” Arxiv, 2504.03773, doi: 10.48550/arXiv.2504.03773. [code]
2. Q. Chen, et al., “CS-SHAP: Extending SHAP to cyclic-spectral domain for better interpretability of intelligent fault diagnosis,” Arxiv, 2502.06424, doi: 10.48550/arXiv.2502.06424. [code]
3. Q. Chen, et al., “Interpreting what typical fault signals look like via prototype-matching,” Advanced Engineering Informatics, vol. 62, p. 102849, Oct. 2024, doi: 10.1016/j.aei.2024.102849. (IF=8.0, ccf-b, TOP)
4. Q. Chen, et al., “TFN: An interpretable neural network with time-frequency transform embedded for intelligent fault diagnosis,” Mechanical Systems and Signal Processing, vol. 207, p. 110952, Jan. 2024, doi: 10.1016/j.ymssp.2023.110952. [Code | 中文介绍] (IF=7.9, TOP, ESI Highly Cited Paper)
5. X. Dong*, Q. Chen*, et al., “A systematic framework of constructing surrogate model for slider track peeling strength prediction,” Science China Technological Sciences, Sep. 2024, doi: 10.1007/s11431-024-2764-5. [Link | Introduction | 中文介绍] (IF=4.4)
6. K. Hu, Q. Chen, et al., “An interpretable deep feature aggregation framework for machinery incremental fault diagnosis,” Advanced Engineering Informatics, May 2025, doi: 10.1016/j.aei.2025.103189. (IF=8.0, ccf-b, TOP)
7. 陈钱, 等. 一种面向机械设备故障诊断的可解释卷积神经网络[J]. 机械工程学报, 2024, 60(12): 65. [中文介绍 | Link]
8. 陈钱, 等. 基于迭代式局部加权线性回归的汽车座椅滑轨剥离强度预测[J]. 机械工程学报, 2024. (In Press)

Patent:

1. X. Dong, Q. Chen, et al., “Data-driven-based automobile seat slide rail peel strength prediction method”, CN116822292A, Sep. 29, 2023.

Project

• 2021.09-2023.03: Development of a predictive system for studying the robustness of car seat slide rail shapes. [detail | 详情 ]
• 2021.08-2022.08: Exploring the interpretability of convolutional neural networks combined with time-frequency transform. [detail | 详情]
• 2020.06-2021.06: Load identification methods for piping systems. [detail]